Vehicle scheduling method and electronic equipment

Abstract

The invention relates to a vehicle scheduling method and electronic equipment, and the method comprises the steps: obtaining the riding demands of a user, and enabling the riding demands to comprise a riding number demand and a riding cost demand; determining all available vehicle queues according to the demand of the number of passengers; and determining the driving path meeting the riding cost requirement in all the driving paths of each passenger vehicle queue as a target driving path, and determining the passenger vehicle queue corresponding to the target driving path as a target vehicle queue. Therefore, the dual requirements of the user on the number of passengers and the cost can be met at a time, the flexibility and adaptability of vehicle scheduling are greatly improved, and efficient travel of the user is ensured.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a vehicle dispatching method and electronic equipment. Background Art

[0002] As a typical application scenario of AI-enabled automotive industry, autonomous driving is not only a new track for the deep integration of digital economy and real economy, but also an important field for developing new quality productivity. Among them, shared autonomous vehicles (SAVs) are a potential mode of travel that is liked and accepted by more and more people. However, the existing autonomous driving fleets mostly operate in a fixed mode, resulting in a relatively simple vehicle dispatching and unable to guarantee efficient travel for users. Summary of the invention

[0003] In view of this, the present application is committed to providing a vehicle dispatching method and electronic equipment, which can effectively improve the flexibility and adaptability of vehicle dispatching and ensure efficient travel for users.

[0004] A first aspect of the present application provides a vehicle dispatching method, comprising:

[0005] Obtaining the user's riding demand; the riding demand includes the riding quantity demand and the riding cost demand;

[0006] According to the vehicle quantity demand, a queue of all available vehicles is determined;

[0007] Among all the driving paths of each of the rideable vehicle queues, a driving path that meets the ride cost requirement is determined as a target driving path, and the rideable vehicle queue corresponding to the target driving path is determined as a target vehicle queue.

[0008] Optionally, the ride quantity requirement includes the number of passengers and the expected number of cabins;

[0009] The step of determining all available vehicle queues according to the vehicle number demand includes:

[0010] Determine all unloaded vehicles in the current road network;

[0011] The vehicles or vehicle combinations that meet the number of passengers and the expected number of cabins among all the unloaded vehicles are determined as the passenger vehicle queue, and all the passenger vehicle queues are obtained.

[0012] Optionally, determining a driving path that meets the riding cost requirement among all driving paths of each of the rideable vehicle queues as a target driving path, and determining the rideable vehicle queue corresponding to the target driving path as a target vehicle queue includes:

[0013] Determine all driving paths of each of the passenger vehicle queues;

[0014] Based on the ant colony algorithm, a driving path that meets the riding cost requirement is determined from each driving path, and the driving path that meets the riding cost requirement is determined as a target driving path, and the available vehicle queue corresponding to the target driving path is determined as a target vehicle queue.

[0015] Optionally, the ride demand also includes a ride location demand;

[0016] The determining of all driving paths of each of the passenger vehicle queues includes:

[0017] Determining the current position of each of the queues of available vehicles;

[0018] All driving paths of each of the queues of available vehicles are determined according to the current positions of each of the queues of available vehicles and the riding position requirements.

[0019] Optionally, the determining a driving path that meets the travel cost requirement from the driving paths based on an ant colony algorithm includes:

[0020] For the available vehicle queue, the corresponding transition probability value of each driving path is calculated, and the fitness cost function value of each driving path is determined according to the riding cost requirement;

[0021] Calculating the pheromone increment of each driving path according to the fitness cost function value of each driving path, iterating the transition probability value multiple times based on the pheromone increment of each driving path, and obtaining the target transition probability value of the rideable vehicle queue on each driving path;

[0022] The target transition probability values ​​of each of the passenger vehicle queues on each of the driving paths are determined and compared, the driving path corresponding to the maximum target transition probability value is determined as the target driving path, and the passenger vehicle queue corresponding to the target driving path is determined as the target vehicle queue.

[0023] Optionally, the travel cost requirement includes minimizing time cost requirement or minimizing economic cost requirement.

[0024] Optionally, the iterating the transition probability value multiple times based on the pheromone increment of each driving path to obtain a target transition probability value of the rideable vehicle queue on each driving path includes:

[0025] The transfer probability value is iterated multiple times based on the pheromone increment of each driving path, and the iteration is stopped when the iteration meets the preset termination condition to obtain the target transfer probability value of the passenger vehicle queue on each driving path; the preset termination condition includes: the difference between the transfer probability value obtained for a consecutive preset number of times and the transfer probability value obtained in the corresponding previous iteration is less than a preset threshold.

[0026] Optionally, after determining the passenger vehicle queue corresponding to the target driving path as the target vehicle queue, the method further includes:

[0027] Based on the target driving path, a driving task is generated, and sent to the target vehicle queue, so that the target vehicle queue performs the driving task based on the corresponding target driving path;

[0028] If feedback is received that the target vehicle queue has completed the driving task, the current position of the target vehicle queue is determined, and the corresponding nearest stop point is determined according to the current position; a stop instruction is generated according to the nearest stop point and sent to the target vehicle queue, so that the target vehicle queue enters the nearest stop point and completes parking.

[0029] Optionally, in the queue of available vehicles, the number of cabins of the vehicles includes: 1 seat, 2 seats, and / or 4 seats.

[0030] A second aspect of the present application provides an electronic device, including:

[0031] A processor, and a memory connected to the processor;

[0032] The memory is used to store computer programs;

[0033] The processor is used to call and execute the computer program in the memory to perform the vehicle dispatching method as described in the first aspect of the present application.

[0034] In the solution of the present application, the user's riding demand can be first obtained, and the riding demand can include the riding quantity demand and the riding cost demand; according to the riding quantity demand, all available vehicle queues can be determined to ensure that the riding demand of different numbers of passengers can be met at a time; then, among all the driving paths of each available vehicle queue, the driving path that meets the riding cost demand is determined as the target driving path, and the available vehicle queue corresponding to the target driving path is determined as the target vehicle queue. In this way, the user's dual demands for the number of passengers and the cost can be met at a time, which greatly improves the flexibility and adaptability of vehicle scheduling and ensures the efficient travel of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 It is a flow chart of a vehicle dispatching method provided by an embodiment of the present application.

[0037] Figure 2 It is a flow chart of a vehicle dispatching method provided by another embodiment of the present application.

[0038] Figure 3 It is a flow chart of a vehicle dispatching method provided by another embodiment of the present application.

[0039] Figure 4 It is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0041] With the acceleration of urbanization, traditional travel modes can no longer meet people's growing travel needs. The development of autonomous driving technology provides new possibilities for solving this problem. However, existing autonomous driving fleets mostly operate in fixed modes, lack flexibility and adaptability, and cannot guarantee users' efficient travel.

[0042] To this end, an embodiment of the present application provides a vehicle dispatching method, such as Figure 1 As shown, the vehicle dispatching method may include at least the following steps:

[0043] S101. Obtain the user's riding demand; the riding demand includes the riding quantity demand and the riding cost demand.

[0044] Taking the execution of the cloud center as an example, users can send ride requirements to the cloud center through the client, so that the cloud center can obtain the user's ride requirements. Among them, the ride quantity requirement is used to represent the number of vehicles required for the user's ride, thus laying the foundation for the subsequent single dispatch of vehicles to meet the ride requirements of different passenger numbers.

[0045] Furthermore, the passenger demand can also represent the number of cabins required by users, which not only lays the foundation for the subsequent single dispatch of vehicles to meet the comfort needs of passengers, but also improves the flexibility of vehicle dispatch. Among them, the number of cabins can include 1 seat, 2 seats and 4 seats. Among them, 1 seat means that it can accommodate 1 person, 2 seats can accommodate 1-2 people, and 4 seats can accommodate 1-4 people.

[0046] S102: Determine a queue of all available vehicles based on the number of passengers required.

[0047] The passenger vehicle fleet may be one vehicle or a combination of multiple vehicles.

[0048] During implementation, the number of cabins in the available vehicle queue may include: 1 seat, 2 seats, and / or 4 seats. In this way, the travel needs of a large number of passengers in a single trip can be met.

[0049] Specifically, when there is only one passenger, the available vehicle queue is one vehicle, and when there are multiple passengers, the available vehicle queue can be a combination of multiple vehicles. For example, when the number of passengers is 8, the available vehicle queue can be two 4-seater vehicles, or 8 1-seater vehicles, or 1 1-seater vehicle, 1 3-seater vehicle, and 1 4-seater vehicle, etc. All available vehicle queues refer to all available vehicles or vehicle combinations that can meet the number of passengers required.

[0050] Determining all available vehicle fleets that can meet the passenger demand can provide a guarantee for further determining available vehicle fleets that better meet user needs.

[0051] It should be noted that the embodiments of the present application are only described using the example that the number of cabins may include 1 seat, 2 seats and / or 4 seats, but the present application is not limited to this. In some other implementations, the number of cabins may also include 3 seats, 6 seats, etc.

[0052] S103: Determine a driving path that meets the riding cost requirement among all driving paths of each passenger vehicle queue as a target driving path, and determine the passenger vehicle queue corresponding to the target driving path as a target vehicle queue.

[0053] The ride cost demand refers to the demand for the lowest cost for users to take a ride, that is, the determined target driving route and the corresponding available vehicle queue can enable users to complete the ride at the lowest cost and reach the final destination. In this way, from the user's perspective, the user's rights and interests are maximized, and while ensuring that user needs are met, the reasonable call of vehicles is realized, increasing the flexibility and adaptability of vehicle matching.

[0054] In this embodiment, the user's riding demand can be first obtained, and the riding demand can include the riding quantity demand and the riding cost demand; according to the riding quantity demand, all available vehicle queues can be determined to ensure that the riding demands of different numbers of passengers can be met at a time; then, among all the driving paths of each available vehicle queue, the driving path that meets the riding cost demand is determined as the target driving path, and the available vehicle queue corresponding to the target driving path is determined as the target vehicle queue. In this way, the user's dual demands on the number of passengers and the cost can be met at a time, which greatly improves the flexibility and adaptability of vehicle scheduling and ensures the efficient travel of users.

[0055] Among them, in the available vehicle queue, the number of cabins of the vehicle may include: 1 seat, 2 seats, and / or 4 seats. In this way, it is convenient to meet the travel needs of users with different bases.

[0056] In some implementations, the ride quantity requirement may include the number of passengers and the desired number of cabins.

[0057] Accordingly, when determining all passenger vehicle queues according to the passenger number demand, all empty vehicles in the current road network can be determined first; then the vehicles or vehicle combinations that meet the number of passengers and the expected number of cabins among all the empty vehicles can be determined as passenger vehicle queues, thereby obtaining all passenger vehicle queues.

[0058] The area range of the current road network can be set according to actual needs and is not specifically limited here. For example, the area range of the current road network can be an area within 10 kilometers around the passenger location, etc.

[0059] During implementation, the number of passengers and the expected number of cabins can be used to meet the riding needs of different numbers of passengers and cabins. While improving user satisfaction, it also improves the flexibility and adaptability of vehicle dispatching.

[0060] For example, the number of passengers provided by the user is 6, and the expected number of cabins is 2 with 3 seats. When determining all available vehicle queues, all 3-seater vehicles among all empty vehicles in the current road network can be screened out and combined in pairs. Each group is a available vehicle queue. In this way, all available vehicle queues can be obtained.

[0061] For another example, the number of passengers provided by the user is 3, and the expected number of cabins is 3 one-seat cabins. Then, when determining all the queues of available vehicles, all the one-seat vehicles among all the empty vehicles in the current road network can be screened out and grouped in groups of three, with every three vehicles forming a queue of available vehicles, thus obtaining the queues of all available vehicles.

[0062] It should be noted that when the number of cabins of an unloaded vehicle cannot meet the expected number of cabins or the user does not provide the expected number of cabins, the number of passengers can be given priority, and the vehicle or vehicle combination that meets the number of passengers is determined as the available vehicle queue in accordance with the principle of minimum total number of vehicles. In addition, when an unloaded vehicle cannot meet the number of passengers, the search for an unloaded vehicle can continue until the unloaded vehicle can meet the number of passengers.

[0063] In some embodiments, Figure 2 As shown, the above step S103 may specifically include the following implementation steps:

[0064] S1031. Determine all driving paths of each passenger vehicle queue.

[0065] A driving path is the path that a fleet of available vehicles needs to travel to deliver passengers to their destinations.

[0066] It should be understood that each vehicle in the available vehicle queue corresponds to at least one driving path, and the vehicle can reach the destination specified by the passenger through the corresponding at least one driving path. Determining all driving paths of each available vehicle queue can lay the foundation for subsequently screening out a driving path that meets the user's riding needs from all driving paths.

[0067] S1032: Determine a driving path that meets the travel cost requirement from each driving path based on the ant colony algorithm, determine the driving path that meets the travel cost requirement as the target driving path, and determine the available vehicle queue corresponding to the target driving path as the target vehicle queue.

[0068] The basic principle of the ant colony algorithm comes from the shortest path principle of foraging in nature. According to the observation of entomologists, ants can find the shortest path from the food source to the nest without any prompts, and can adaptively search for a new optimal path after the environment changes. In the process of ants looking for food, the transition probability is mainly based on their pheromones and the heuristic information of each path. This process is analogous to the exploration process of the target driving path, that is, it is transformed into a problem of searching for the best path from the passenger's own position to the passenger's initial position and then to the passenger's desired terminal position by a passenger vehicle queue.

[0069] By combining the ant colony algorithm with the travel cost requirements, the target driving path that best meets the user's travel cost requirements can be screened out from multiple driving paths, thereby determining the corresponding fleet of available vehicles. In this way, while taking into account the user's personalized needs, it avoids the waste of resources caused by unreasonable vehicle scheduling, and improves vehicle scheduling efficiency and user satisfaction.

[0070] In some implementations, the ride demand may also include a ride location demand.

[0071] Accordingly, when determining all driving paths of each passenger vehicle queue, the current position of each passenger vehicle queue can be determined first; and then all driving paths of each passenger vehicle queue can be determined based on the current position of each passenger vehicle queue and the passenger position requirements.

[0072] The driving path refers to the path of the available vehicle queue from the current position through the passenger's initial position to the passenger's required terminal position. Correspondingly, the riding position requirement may include the passenger's initial position and the passenger's required terminal position.

[0073] By determining all driving paths corresponding to each available vehicle through the riding position requirements, it can be ensured that all driving paths of the available vehicle queue can meet the user's riding position requirements, providing a guarantee for the target driving path determined subsequently to meet the user's riding position requirements.

[0074] Specifically, when determining a driving path that meets the travel cost requirement from various driving paths based on the ant colony algorithm, the transfer probability value of each corresponding driving path can be calculated for the passenger vehicle queue, and the fitness cost function value of each driving path can be determined according to the travel cost requirement; the pheromone increment of each driving path is calculated according to the fitness cost function value of each driving path, and the transfer probability value is iterated multiple times based on the pheromone increment of each driving path to obtain the target transfer probability value of the passenger vehicle queue on each driving path; the target transfer probability value of each passenger vehicle queue on each driving path is determined and compared, the driving path corresponding to the largest target transfer probability value is determined as the target driving path, and the passenger vehicle queue corresponding to the target driving path is determined as the target vehicle queue.

[0075] The fitness cost function is used to characterize the cost consumption incurred by the passenger vehicle queue to complete the corresponding driving path. Different driving paths will have different fitness cost function values.

[0076] In the ant colony algorithm, ants will rely on pheromone concentration to select paths, and using pheromone increments to update pheromones can help ants strengthen the optimal solution path, while improving the ability to explore new solutions and avoid falling into local optimal situations. During implementation, using the fitness cost function value to determine the corresponding pheromone increment can help the algorithm explore the optimal path that meets the cost requirements of riding. That is, the optimal driving path that meets the cost requirements of riding can be determined through the iterative transition probability value. Specifically, the driving path with the largest transition probability value can be determined as the target driving path that meets the cost requirements of riding. Correspondingly, the passenger vehicle queue corresponding to the target driving path is the target vehicle queue.

[0077] In specific implementation, the travel cost requirement may include minimizing the time cost requirement or minimizing the economic cost requirement.

[0078] Among them, the demand for minimizing economic costs refers to the demand for the lowest economic cost for users to take the bus, and the demand for minimizing time costs refers to the demand for the shortest time spent by users to take the bus.

[0079] In the application, users can determine whether the cost requirement of the ride is to minimize the time cost requirement or minimize the economic cost requirement according to their own needs. Specifically, if the user hopes to reach the destination quickly, he can choose to provide the minimum time cost requirement; if the user hopes to reach the destination at the lowest price, he can choose to provide the minimum economic cost requirement; in addition, the user can also choose to provide a balanced cost requirement or not make a choice. If the user chooses the balanced cost requirement or does not make a choice, the default is to determine the minimum time cost requirement.

[0080] It should be noted that in the embodiments of the present application, it is only illustrated by way of example that the user chooses to balance the cost requirements or the user does not make a choice corresponding to the minimization of the time cost requirement, but the present application is not limited to this. In some other implementations, the user chooses to balance the cost requirements or the user does not make a choice corresponding to the minimization of the economic cost requirement or other requirements, and so on.

[0081] In specific implementation, the waiting time and travel time consumption of passengers are mainly related to the current position of the passenger vehicle queue, the distance between the passenger's initial position and the passenger's final position. In other words, the fitness function value corresponding to the minimum time cost requirement is mainly related to the distance between the current position of the passenger vehicle, the passenger's initial position and the passenger's final position. Accordingly, the fitness function corresponding to the minimum time cost requirement can be set accordingly, and no specific limitation is made here. The economic consumption of passengers' travel is mainly related to the fuel consumption of the passenger vehicle queue, the total driving distance and the specific road conditions. In other words, the fitness function corresponding to the minimum economic cost requirement is mainly related to the fuel consumption of the passenger vehicle queue, the total driving distance and the specific road conditions. Accordingly, the fitness function corresponding to the minimum economic cost requirement can be set accordingly, and no specific limitation is made here.

[0082] In some embodiments, when the transfer probability value is iterated multiple times based on the pheromone increment of each driving path to obtain the target transfer probability value of the passenger vehicle queue on each driving path, the transfer probability value can be iterated multiple times based on the pheromone increment of each driving path, and when the iteration meets the preset termination condition, the iteration is stopped to obtain the target transfer probability value of the passenger vehicle queue on each driving path; the preset termination condition may include: the difference between the transfer probability value obtained for a consecutive preset number of times and the transfer probability value obtained in the corresponding previous iteration is less than a preset threshold.

[0083] Among them, the preset threshold can be set according to actual needs and is not specifically limited here.

[0084] During implementation, when the iteration meets the preset termination condition, that is, the iteration converges, at this time, the target transfer probability value of each passenger vehicle queue on each driving path can be obtained, and the maximum value of the target transfer probability value of each passenger vehicle queue on each driving path is determined as the local optimal solution of each passenger vehicle queue. Then, the local optimal solutions of each passenger vehicle queue are compared, and the maximum value therein is determined as the global optimal solution. In other words, the driving path corresponding to the maximum value of all target transfer probability values ​​is determined as the target driving path, and the passenger vehicle queue corresponding to the target driving path is determined as the target vehicle queue. In this way, the target vehicle queue travels based on the target driving path, which can meet the user's travel cost requirements and ensure the rationality and efficiency of vehicle resource scheduling.

[0085] In some implementations, after the passenger vehicle queue corresponding to the target driving path is determined as the target vehicle queue, Figure 3 As shown, the vehicle dispatching method may further include the following steps:

[0086] S104: Generate a driving task based on the target driving path, and send it to the target vehicle queue, so that the target vehicle queue performs the driving task based on the corresponding target driving path.

[0087] After the target driving path is determined, a driving task is generated based on the target driving path and sent to the target vehicle queue, which can realize the reasonable call of the target vehicle queue and at the same time meet the user's personalized riding needs.

[0088] S105. If feedback is received that the target vehicle queue has completed the driving task, the current position of the target vehicle queue is determined, and the corresponding nearest stop point is determined according to the current position; a stop instruction is generated according to the nearest stop point and sent to the target vehicle queue, so that the target vehicle queue drives into the nearest stop point to complete parking.

[0089] If feedback is received that the target vehicle queue has completed the driving task, it means that the target vehicle queue has delivered the passengers to the destination. In order to ensure the timeliness and effectiveness of vehicle scheduling, the current position of the target vehicle queue can be determined, thereby providing a basis for reasonably planning the parking route of the target vehicle queue.

[0090] Sending a parking instruction to the target vehicle queue enables the target vehicle queue to automatically drive to the nearest parking point to complete parking after completing the driving task, realizing the intelligent management of unloaded vehicles, avoiding the occurrence of parking chaos, and at the same time providing a guarantee for timely response to driving tasks.

[0091] Furthermore, for ease of understanding, the specific implementation methods of this application are described in more detail below with the vehicle-road collaborative cloud center as the execution entity:

[0092] First, define the current road network area as a directed graph G = (V, W), where V is a vertex set representing road nodes in the current road network; W is a directed edge representing a road segment in the current road network.

[0093] Define the ride demand N = (O, D, n, Ω0, π p ), where O represents the initial position of the passenger, D is the final position of the passenger, n is the number of passengers, and Ω0 is the expected number of cabins. p Set the cost demand for riding. If the passenger chooses to minimize the time cost demand, it is expressed as π p =minJ(π p ) time ; If the passenger chooses to minimize the economic cost demand, it is expressed as π p =minJ(π p ) cost ; If the passenger chooses to balance the cost demand or makes no choice, it is expressed as π p =minJ(π p ) balance .

[0094] Defining SAV attributes in, represents the vehicle number, j=1, 2, 3…n is the number item, S represents the driving status of the SAV, Ω={1,2,4} represents the number of SAV cabins, representing 1 cabin, 2 cabins and 4 cabins respectively, ω∈[0,1] represents the load factor, which directly reflects the passenger status. For example, ω=0 means that the SAV load status is empty; ω=1 means that the SAV load status is fully loaded.

[0095] Users (passengers) can send demands through the client N = (O, D, n, Ω0, π p ) to the vehicle-road collaborative cloud center.

[0096] The travel cost demand setting means that the preference for the minimum time cost, the lowest economic cost or a balance between the two is desired for this trip so as to optimize the system combination.

[0097] The ride demand N provided by the vehicle-road cooperative cloud center to the client is (O, D, n, Ω0, π p ) to extract and analyze data, the passenger number interval determination module makes an interval determination on the number of passengers, and the SAV matching module matches the passenger with a single SAV or a combination of SAV queues with an appropriate number of cabins according to the passenger number interval. When matching SAVs with different cabins, the system gives priority to matching the passenger's expected number of cabins Ω0; if That is, when the passenger does not select the desired number of cabins, the SAV matching module performs matching according to the corresponding matching mode, specifically:

[0098] Case 1: 1≤n≤4, SAV single-vehicle matching mode:

[0099] When 1≤n≤4, the SAV matching module matches the passenger with a SAV of type Ω=n (if n=3, it will automatically match a SAV of type Ω=4). At this time, the data storage and processing module of the vehicle-road cooperative cloud center searches for all SAV vehicles with ω=0 (empty) in the SAV sequence database in the current road network area G=(V,W), and generates an initial feasible SAV sequence set (each passenger vehicle queue), with the current horizontal coordinate of the SAV Set represents the SAV sequence set: Where, l represents the number of available SAV fleets, i=1,…n represents all unloaded SAV sequence sets in the SAV sequence database, and n is the number of SAVs.

[0100] Case 2: n>4, SAV queue matching mode:

[0101] When n>4, the 4-seat SAV can no longer meet the passenger demand. At this time, the system starts the SAV queue matching mode, that is, SAVs with different cabin numbers are combined into a queue suitable for the number of passengers. At this time, the data storage and processing module of the vehicle-road collaborative cloud center searches for all SAV vehicles with ω=0 in the SAV sequence database in the current road network area G=(V,W) and generates a passenger SAV queue.

[0102] k,m,q∈Z, Z represents an integer, k, m and q represent the number of 1-seat, 2-seat and 4-seat SAVs in the combined queue, respectively, and k×2m×4q=n. Specifically, when generating a rideable SAV queue, a queue combination with a total number of n SAVs can be generated in the current road network area G=(V,W). If the combination in the current road network area cannot satisfy k×2m×4q=n, the minimum total number of SAVs principle is followed to match passengers with a queue combination with a total number of cabins greater than the number of passengers.

[0103] The basic principle of the ant colony algorithm comes from the shortest path principle of foraging in nature. According to the observation of entomologists, ants can find the shortest path from the food source to the nest without any prompts, and can adaptively search for a new optimal path after the environment changes. In the process of ants looking for food, the state transition probability is mainly based on their pheromones and the heuristic information of each path. This process is analogous to the SAV matching process, that is, it is transformed into the problem of SAV searching for the best path from its own starting position to the passenger's initial position and then to the passenger's required terminal position.

[0104] Specifically, suppose that in the current road network area G = (V, W), at time t, the vehicle located at the initial position of the SAV V a Pathway Ants (SAV) Move to the target location road node V b The process transition probability Calculated as:

[0105]

[0106] In the formula, is the SAV from the road node V at time t a Move to road node V b , α is the pheromone concentration factor, β is the expected heuristic factor, is the time from the road node V a To road node V b The path heuristic information is calculated as follows:

[0107]

[0108] In the formula, is the road node V a With road node V b The Euclidean distance between .

[0109] The pheromone update process aims to achieve solution reinforcement, exploration and optimization by imitating the foraging behavior of ants in nature. The update mechanism ensures that the algorithm maintains the ability to explore new solutions while strengthening the optimal solution path, avoiding falling into local optimality. Reasonable design and adjustment of pheromone update rules can greatly improve the direction and efficiency of the dynamic adjustment search process and the optimization and resource allocation in SAV matching. Pheromone updates include volatilization mechanism updates and incremental mechanism updates.

[0110] To avoid premature convergence to the local optimal solution, pheromones will gradually evaporate over time. The pheromone evaporation mechanism update refers to the SAV from V a To V b , the update rules are as follows:

[0111]

[0112] Where θ is the pheromone volatility coefficient, Reflects the rate at which pheromones weaken over time.

[0113] Incremental mechanism update means that when all SAVs perform iterative search, the current optimal path is strengthened by adding pheromones. The rules are designed as follows:

[0114]

[0115] ρ is the global pheromone volatility coefficient, (1-ρ) is the pheromone residual factor, The increment of pheromone concentration on the path during the current SAV iterative search. is the SAV vehicle on the current path The concentration of pheromones left behind. When searching for a matching path, the ant colony (SAV) will leave pheromones based on the quality of its path (usually related to the objective function value, such as path length, cost, time, etc.). The increment of pheromones is usually inversely proportional to the fitness of the path (e.g., the quality of the path), which is expressed as follows:

[0116]

[0117] Where J is the fitness cost function for searching matching paths. Q is the constant of pheromone increment, which is used to control the amount of pheromone increase. The size of Q directly affects the increment of pheromone. A larger Q will result in a larger increment of each path, thereby enhancing the attractiveness of the path; a smaller Q will result in a smaller pheromone update and a weaker path attraction. In practical problems, the determination of Q should be based on the distance from the starting position to the end position and the initial node V. a To the target node V b The number of road nodes between V Accordingly, in the embodiments of the present application,

[0118] In order to comprehensively consider the SAV matching quality and output personalized matching strategies at the same time, a fitness cost function is set, taking into account the following aspects: (1) Passenger time cost J(π p ) time :The waiting time and travel time of passengers are mainly related to the initial position of the SAV and the distance between the passenger’s starting position and the destination. (2) Passenger economic cost J(π p ) cost :The economic consumption of passengers’ travel is mainly related to SAV fuel consumption, total driving distance and specific road conditions.

[0119] If the passenger chooses to minimize the time cost, that is, π p =minJ(π p ) time , the smaller the time cost, the larger the value of the fitness cost function, and the corresponding fitness cost function is as follows:

[0120]

[0121] The expression of the improved pheromone increment is as follows:

[0122]

[0123] At this time, the smaller the time cost, the greater the SAV pheromone increment. The larger it is, the path with the larger SAV transfer probability value matching the current ride demand.

[0124] If the passenger chooses to minimize the economic cost, that is, π p =minJ(π p ) cost , the smaller the economic cost, the greater the fitness, and the corresponding fitness cost function is as follows:

[0125]

[0126] The expression of the improved pheromone increment is as follows:

[0127]

[0128] At this time, the smaller the economic cost, the greater the increase in SAV pheromone. The larger it is, the path with the larger SAV transfer probability value matching the current ride demand.

[0129] If the passenger chooses to balance the cost or makes no choice, that is, π p =minJ(π p ) balance , the default is to minimize economic cost.

[0130] It should be noted that when the rideable vehicle queue is a single vehicle, the transition probability value of the rideable vehicle queue is the product of the first transition probability value and the second transition probability value, wherein the first transition probability value is the transition probability value of the path corresponding to the current position of the rideable vehicle queue to the initial position of the passenger, and the second transition probability value is the transition probability value of the path corresponding to the initial position of the passenger to the terminal position of the rideable vehicle queue. When the rideable vehicle queue is a combination of multiple vehicles, the transition probability value of the rideable vehicle queue is the product of the transition probability values ​​of the multiple vehicles.

[0131] In summary, based on the number of passengers and the expected number of cabins, the passenger is finally matched with the driving path with the highest transfer probability value among all the driving paths of the available vehicle queues. The vehicle-road collaborative cloud center transmits the driving task to the information instruction receiving and sending center of the corresponding SAV through the SAV interaction and information release module. After receiving the driving task, the SAV information instruction receiving and sending center completes the passenger transportation task through the vehicle decision control system.

[0132] As another optional implementation of the contents disclosed in the present application, an embodiment of the present application further provides a vehicle dispatching device, which may at least include: an acquisition module, used to acquire the user's riding demand; the riding demand includes the riding quantity demand and the riding cost demand; a first determination module, used to determine all passenger vehicle queues according to the riding quantity demand; a second determination module, used to determine the driving path that meets the riding cost demand among all driving paths of each passenger vehicle queue as the target driving path, and determine the passenger vehicle queue corresponding to the target driving path as the target vehicle queue.

[0133] Optionally, the passenger quantity demand includes the number of passengers and the expected number of cabins; accordingly, when determining all passenger vehicle queues based on the passenger quantity demand, the first determination module can be specifically used to: determine all empty vehicles in the current road network; determine the vehicles or vehicle combinations that meet the number of passengers and the expected number of cabins among all empty vehicles as passenger vehicle queues, and obtain all passenger vehicle queues.

[0134] Optionally, the second determination module can be specifically used to: determine all driving paths of each passenger vehicle queue; determine a driving path that meets the riding cost requirement from each driving path based on an ant colony algorithm, and determine the driving path that meets the riding cost requirement as a target driving path, and determine the passenger vehicle queue corresponding to the target driving path as a target vehicle queue.

[0135] Optionally, the riding demand also includes the riding position demand; accordingly, when determining all driving paths of each passenger vehicle queue, the second determination module can be specifically used to: determine the current position of each passenger vehicle queue; and determine all driving paths of each passenger vehicle queue based on the current position of each passenger vehicle queue and the riding position demand.

[0136] Optionally, when determining a driving path that meets the travel cost requirement from various driving paths based on the ant colony algorithm, the second determination module can be specifically used to: calculate the transfer probability value of each corresponding driving path for the passenger vehicle queue, and determine the fitness cost function value of each driving path according to the travel cost requirement; calculate the pheromone increment of each driving path according to the fitness cost function value of each driving path, and iterate the transfer probability value multiple times based on the pheromone increment of each driving path to obtain the target transfer probability value of the passenger vehicle queue on each driving path; determine the target transfer probability value of each passenger vehicle queue on each driving path and compare them, determine the driving path corresponding to the largest target transfer probability value as the target driving path, and determine the passenger vehicle queue corresponding to the target driving path as the target vehicle queue.

[0137] Optionally, the travel cost requirement includes minimizing time cost requirement or minimizing economic cost requirement.

[0138] Optionally, when the transfer probability value is iterated multiple times based on the pheromone increment of each driving path to obtain the target transfer probability value of the passenger vehicle queue on each driving path, the second determination module can be specifically used to: iterate the transfer probability value multiple times based on the pheromone increment of each driving path, and stop the iteration when the iteration meets the preset termination condition to obtain the target transfer probability value of the passenger vehicle queue on each driving path; the preset termination condition includes: the difference between the transfer probability value obtained for a consecutive preset number of times and the transfer probability value obtained in the corresponding previous iteration is less than a preset threshold.

[0139] Optionally, the vehicle dispatching device may further include a generating and sending module, which may specifically include: generating a driving task based on a target driving path, and sending it to a target vehicle queue, so that the target vehicle queue performs the driving task based on the corresponding target driving path; if feedback is received that the target vehicle queue has completed the driving task, determining the current position of the target vehicle queue, and determining the corresponding nearest stop point based on the current position; generating a stop instruction based on the nearest stop point and sending it to the target vehicle queue, so that the target vehicle queue drives into the nearest stop point to complete parking.

[0140] Optionally, in the fleet of available vehicles, the number of cabins of the vehicles includes: 1 seat, 2 seats, and / or 4 seats.

[0141] The specific implementation of the vehicle dispatching device provided in the embodiments of the present application can refer to the implementation of the vehicle dispatching method described in any of the above embodiments, which will not be repeated here.

[0142] As another optional implementation of the content disclosed in this application, an embodiment of this application further provides an electronic device, such as Figure 4 As shown, the electronic device may include: a memory 401 and a processor 402; wherein the memory 401 is connected to the processor 402 and is used to store programs; the processor 402 is used to implement the vehicle scheduling method disclosed in any of the above-mentioned embodiments by running the program stored in the memory 401.

[0143] Specifically, the electronic device may further include: a bus, a communication interface 403 , an input device 404 and an output device 405 .

[0144] The processor 402, the memory 401, the communication interface 403, the input device 404 and the output device 405 are connected to each other via a bus.

[0145] A bus may include a pathway that transfers information between components of a computer system.

[0146] Processor 402 may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0147] The processor 402 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0148] The memory 401 stores a program for executing the technical solution of the present application, and may also store an operating system and other key services. Specifically, the program may include a program code, and the program code includes computer operation instructions. More specifically, the memory 401 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk storage, a flash, and the like.

[0149] The input device 404 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor.

[0150] Output device 405 may include a device that allows information to be output to a user, such as a display screen, a printer, a speaker, etc.

[0151] The communication interface 403 may include any transceiver or the like to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0152] The processor 402 executes the program stored in the memory 401 and calls other devices, which can be used to implement each step of the vehicle scheduling method provided in the above-mentioned embodiment of the present application.

[0153] An embodiment of the present application also provides a vehicle-road cooperative system, which may include an electronic device as described in any of the above embodiments.

[0154] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a computer, the computer executes the vehicle dispatching method in any of the above embodiments.

[0155] An embodiment of the present application further provides a computer program product comprising instructions, which, when executed by a computer, enables the computer to execute the vehicle dispatching method described in any of the above embodiments.

[0156] It should be understood that the specific examples herein are only intended to help those skilled in the art to better understand the embodiments of the present specification, rather than to limit the scope of the present invention.

[0157] It can be understood that in the various implementations of this specification, the size of the sequence number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the implementation methods of this specification.

[0158] It can be understood that the various embodiments described in this specification can be implemented individually or in combination, and the embodiments of this specification are not limited to this.

[0159] Unless otherwise specified, all technical and scientific terms used in the embodiments of this specification have the same meaning as those generally understood by those skilled in the art of the technical field of this specification. The terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the scope of this specification. The term "and / or" used in this specification includes any and all combinations of one or more related listed items. The singular forms of "a", "above", and "the" used in the embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0160] It can be understood that the processor of the embodiment of this specification can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method implementation can be completed by the hardware integrated logic circuit or software instructions in the processor. The above processor can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiment of this specification can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of this specification can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor are combined and executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0161] It is understood that the memory in the embodiments of this specification may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (programmable ROM, PROM), an erasable programmable read-only memory (erasablePROM, EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory may be a random access memory (RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0162] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this specification.

[0163] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method implementation methods and will not be repeated here.

[0164] In the several embodiments provided in this specification, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0165] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0166] In addition, each functional unit in each embodiment of the present specification may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0167] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this specification, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of this specification. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0168] The above is only a specific implementation of this specification, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in this specification, which should be included in the protection scope of this specification. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A vehicle dispatching method, characterized in that: include: Obtaining the user's riding demand; the riding demand includes the riding quantity demand and the riding cost demand; According to the vehicle quantity demand, a queue of all available vehicles is determined; Among all the driving paths of each of the rideable vehicle queues, a driving path that meets the ride cost requirement is determined as a target driving path, and the rideable vehicle queue corresponding to the target driving path is determined as a target vehicle queue.

2. The method according to claim 1, characterized in that The vehicle quantity requirement includes the number of passengers and the expected number of cabins; The step of determining all available vehicle queues according to the vehicle number demand includes: Determine all unloaded vehicles in the current road network; The vehicles or vehicle combinations that meet the number of passengers and the expected number of cabins among all the unloaded vehicles are determined as the passenger vehicle queue, and all the passenger vehicle queues are obtained.

3. The method according to claim 1, characterized in that The step of determining a driving path that meets the riding cost requirement among all driving paths of each of the rideable vehicle queues as a target driving path, and determining the rideable vehicle queue corresponding to the target driving path as a target vehicle queue includes: Determine all driving paths of each of the passenger vehicle queues; Based on the ant colony algorithm, a driving path that meets the riding cost requirement is determined from each driving path, and the driving path that meets the riding cost requirement is determined as a target driving path, and the available vehicle queue corresponding to the target driving path is determined as a target vehicle queue.

4. The method according to claim 3, characterized in that: The riding demand also includes riding position demand; The determining of all driving paths of each of the passenger vehicle queues includes: Determining the current position of each of the queues of available vehicles; All driving paths of each of the queues of available vehicles are determined according to the current positions of each of the queues of available vehicles and the riding position requirements.

5. The method according to claim 3, characterized in that: The step of determining a driving path that meets the travel cost requirement from each driving path based on an ant colony algorithm includes: For the available vehicle queue, the corresponding transition probability value of each driving path is calculated, and the fitness cost function value of each driving path is determined according to the riding cost requirement; Calculating the pheromone increment of each driving path according to the fitness cost function value of each driving path, iterating the transition probability value multiple times based on the pheromone increment of each driving path, and obtaining the target transition probability value of the rideable vehicle queue on each driving path; The target transition probability values ​​of each of the passenger vehicle queues on each of the driving paths are determined and compared, the driving path corresponding to the maximum target transition probability value is determined as the target driving path, and the passenger vehicle queue corresponding to the target driving path is determined as the target vehicle queue.

6. The method according to claim 5, characterized in that The travel cost requirement includes a requirement to minimize time cost or a requirement to minimize economic cost.

7. The method according to claim 5, characterized in that The step of iterating the transition probability value multiple times based on the pheromone increment of each driving path to obtain a target transition probability value of the passenger vehicle queue on each driving path includes: The transfer probability value is iterated multiple times based on the pheromone increment of each driving path, and the iteration is stopped when the iteration meets the preset termination condition to obtain the target transfer probability value of the passenger vehicle queue on each driving path; the preset termination condition includes: the difference between the transfer probability value obtained for a consecutive preset number of times and the transfer probability value obtained in the corresponding previous iteration is less than a preset threshold.

8. The method according to claim 1, characterized in that: After determining the passenger vehicle queue corresponding to the target driving path as the target vehicle queue, the method further includes: Based on the target driving path, a driving task is generated, and sent to the target vehicle queue, so that the target vehicle queue performs the driving task based on the corresponding target driving path; If feedback is received that the target vehicle queue has completed the driving task, the current position of the target vehicle queue is determined, and the corresponding nearest stop point is determined according to the current position; a stop instruction is generated according to the nearest stop point and sent to the target vehicle queue, so that the target vehicle queue enters the nearest stop point and completes parking.

9. The method according to claim 1, characterized in that: In the passenger vehicle queue, the number of cabins of the vehicles includes: 1 seat, 2 seats, and / or 4 seats.

10. An electronic device, characterized in that: include: A processor, and a memory connected to the processor; The memory is used to store computer programs; The processor is used to call and execute the computer program in the memory to perform the vehicle dispatching method as described in any one of claims 1-9.

Images